Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/omarshahine/restaurant-cli/agents-mdgit clone --depth 1 https://github.com/omarshahine/restaurant-cliWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00631 | $0.00631 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
restaurant-cli AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clawpatch Code Review
This repo uses Clawpatch for local automated code review. Keep .clawpatch/ ignored; it is generated runtime state containing features, findings, reports, runs, and patch attempts.
Standard workflow:
clawpatch doctor
clawpatch init # first time only
clawpatch map
clawpatch review --limit 10
clawpatch report --output .clawpatch/reports/summary.md
clawpatch show --finding <id>
clawpatch fix --finding <id>
clawpatch revalidate --finding <id>
If this repo needs hand-authored feature coverage, keep those curated definitions in tools/clawpatch/features/ and sync/copy them into .clawpatch/features/ before review. Do not commit .clawpatch/ generated state.
Imported Claude Project Memory
Durable memory promoted from ~/.claude/projects/-Users-omarshahine-GitHub-restaurant-cli/memory during the AGENTS.md migration. Keep this section current when project-specific operating knowledge changes.
memory/MEMORY.md
- No "goat" in command/feature names — never use the word "goat" in command names, flags, or user-facing copy when porting from table-reservation-goat
memory/feedback_no_goat_naming.md
name: No "goat" in command/feature names description: Never use the word "goat" in restaurant-cli command names, flags, or user-facing copy when porting from table-reservation-goat type: feedback originSessionId: 9bf75f31-0ab9-4a07-bd45-3048d6703916
Do not use the word "goat" anywhere in restaurant-cli command names, flag names, subcommand names, or user-facing copy.
Why: Stated preference while porting features from the table-reservation-goat CLI. The cross-network unified-search command in that tool is literally named goat — when porting, pick a different name.
How to apply: When porting table-reservation-goat features, rename the goat command (the cross-network/multi-provider unified search). Either roll its behavior into the existing search command (default to fan-out across all providers, use --provider to scope) or pick a neutral name like find, across, or any. Other trg names (earliest, drift, watch, sync) are fine to keep as-is — only "goat" is off-limits. Also avoid it in docs, help text, and skill copy.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 45 lines · 631 tokens per session scan A d36867eff3ca
restaurant-cli AGENTS.md is an instructions file published in the GitHub repository omarshahine/restaurant-cli (7 stars, last pushed 29d ago), licensed MIT. It adds 631 tokens to every session, about $0.0032 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ClawTeam-OpenClaw CLAUDE.md
Instructions for win4r/ClawTeam-OpenClaw, covering claude.md, what this project is, common commands, dev install (from repo root) and cli entry points.
tweetclaw AGENTS.md
Instructions for Xquik-dev/tweetclaw: Each commit must reduce net handwritten source LOC. No exceptions. No one may waive this rule. Additions require larger, useful simplifications elsewhere in this repository. Formatting, minification, generated files, and deleted valuable tests or docs do not count.
tokenjuice AGENTS.md
Instructions for vincentkoc/tokenjuice, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and host integrations.
claw-empire AGENTS.md
Instructions for GreenSheep01201/claw-empire, covering claw-empire orchestration rules, language rule, default skill bootstrap, workflow orchestration (additive) and 1) plan node default.
QClaw AGENTS.md
Instructions for QuantumClaw/QClaw, covering agents.md — for ai coding agents, project overview, architecture, conventions and running.
openclaw-onebot AGENTS.md
Instructions for LSTM-Kirigaya/openclaw-onebot, covering openclaw onebot 插件开发指南, 项目概述, 技术栈, 核心依赖 and 项目结构.